Hello,
I am running a SUR on an unbalanced panel dataset. The dependent variables are different production costs for the same product (when added together, they are equal to total production cost). I was wondering whether:
1) STATA provides an intercept for the different equations (that I do not currently obtain)
2) it is possible to correct the standard errors for heteroskedasticity (when adding the option robust, STATA does not produce any different result)
3) the results are a fixed or a random effect model. Reading the original paper by Minh Cong Nguyen it seems that the model is a random effect one, yet I am not completely sure of this. Besides, I run xtsur with both the re and fe options and obtained the same results
4) the issue concerning missing observations (or observations with value very close to zero) has been resolved. The problem is that STATA shows the message "estimates post: matrix has missing values".
I was looking for older posts on all these matters, but I couldn't find any useful information. I would appreciate any clarification.
Thanks,
Federico
Please consider the environment before printing this email.
De informatie verzonden met dit e-mailbericht is vertrouwelijk en uitsluitend bestemd voor de geadresseerde. Indien u als niet-geadresseerde dit bericht ontvangt, wordt u verzocht direct de afzender hierover te informeren en het bericht te vernietigen. Gebruik van informatie door onbevoegden, openbaarmaking of vermenigvuldiging is verboden en kan leiden tot aansprakelijkheid. De afzender is niet aansprakelijk in geval van onjuiste overbrenging van het e-mailbericht en/of bij ontijdige ontvangst daarvan.
The information transmitted is confidential and intended only for the person or entity to whom or which it is addressed. If you are not the intended recipient of this communication, please inform us immediately and destroy this communication. Unauthorised use, disclosure or copying of information is strictly prohibited and may entail liability. The sender accepts no liability for improper transmission of this communication nor for any delay in its receipt.
